Policies
Table of contents
Presentation of Course Material
Overview
This course will be taught in a seminar style, with lectures, 6 homeworks, 5 assigned projects, 1 midterm, weekly paper presentations (2 per person), and a final project. All submissions will go through Gradescope (Course Entry Code: WVK62G). An Ed page has been created for students to discuss homeworks and projects.
Each week, there are 3 hours of lecture, 1 hour of discussion, and 1 hour of organized paper-reading time in lab sections. All of these and office hours will be hosted in-person. You are expected to work on projects during your own time. A booking system will be instituted to reserve robots, and lab TAs will be availble to address any questions during their office hours. Lecture and discussion sections will be recorded and posted, so you may attend these asynchronously. However, due to the journal club nature of lab sections, they will not be offered asynchronously, and you are expected to attend your lab section every week.
Lecture
Lecture will be Tuesday and Thursday from 2:00pm to 3:30pm in North Gate 105. Lectures will be recorded for asynchronous viewing, though we highly recommend you attend live in order to ask questions and engage fully with the material.
Discussions
Discussion sections will be on Wednesday from 1-2pm and Friday from 2-3pm, room TBD. They will have a review of important topics and go over practice problems related to the material to supplement lecture content.
Homeworks
Homeworks will be collected and graded using the Gradescope system. Create an account on gradescope.com with your Berkeley email account and SID. Add this course with the code WVK62G.
Each student is allocated 5 total days of extension, to be used on any homework assignment with no loss of points. To allow for homework solutions to be released in a timely manner, no more than 2 extension days may be used on a single assignment. No homework will be accepted past two days of extension.
Collaboration on homework sets is encouraged, but all students must write up their own solution set. Additionally, every student is accountable for the solutions they submit and may be asked to discuss them with a GSI or instructor. Please list all collaborators at the top of each submitted homework set.
We will hold weekly homework/project parties! They will be held each Monday 6:00pm - 8:00pm. They will be staffed by one or more TAs to assist students working collaboratively through the homework or project.
| Homework | Date Assigned | Due Date |
| Homework 1: Dynamical Systems | 1/18 | 1/24 |
| Homework 2: Controls | 1/25 | 2/7 |
| Homework 3: Path Planning | 2/8 | 2/22 |
| Homework 4: Filtering and Vision | 3/8 | 3/21 |
| Homework 5: Grasping | 3/22 | 4/18 |
| Homework 6: Optimal Control & RL | 4/20 | 5/7 |
Projects
Projects in 106B/206B delve into active areas of research and as a result are more open-ended than labs in 106A. There are no official checkoffs. Instead, students will work on their own time and turn in a report to Gradescope. Project reports will focus on building the skills required to write scientific literature. Slip days may not be used on project submissions.
The lab in Cory 105 is open for use for the projects and the final project. The robots/hardware will be shared. Similar to how final projects in C106A worked, we will organize the robots’ time using a reservation systems.
Projects will be done in groups of 3, but groups of 2 are also acceptable. Each team may only reserve 2 hours at a time and can only make a new reservation once all of the team’s existing reservation times have ended. If a team is caught abusing this policy and overbooking, a 50% penalty will be deducted from the group’s project grade. Each project team will be assigned to a robot. Please reserve times on the following calendars:
- Arm Robot Calendars
- Turtlebot Calendars
- Soft Robot Calendars
Similar to homeworks, each student is allocated 5 total slip days, with no more than 2 extension days for a single project. These are counted separately from homework slip days.
| Project | Date Assigned | Due Date |
| Lab 0: Review of ROS | 1/18 | N/A |
| Project 1A: Trajectory Tracking with Sawyer | 1/18 | 1/31 |
| Project 1B: Trajectory Tracking with Sawyer | 2/1 | 2/14 |
| Project 2: Nonholonomic Control | 2/15 | 3/14 |
| Project 3: State Estimation | 3/15 | 4/7 |
| Project 4: Decentralized Multi-Agent Control | 4/5 | 4/28 |
Midterm
There will be one midterm to ensure students are caught up with course material. It will be a take-home exam that can be completed during any time in a three day window, from 4/19 to 4/21. Logistics will be released closer to the test dates.
Lab Sections and Paper Presentations
Lab sections are not offered asynchronously. At the beginning of lab section, the GSI will go over any announcements, including introducing any new projects. Then, there will be a discussion of two assigned papers.
Each student will be responsible for presenting two papers to their lab section through the course of the semester. This presentation should be around 20 minutes long, and you will be graded based on your level of insight on the material and your ability to answer questions from course staff and other students. You have the option of working with a partner or two for this. Details are to be finalized by the second week of class.
After the paper discussions, if there is time remaining, labs will be more free-form and similar in style to office hours. You are encouraged to use this time to work with your group on projects and ask questions.
Final Project
The final project will constitute the largest single portion of your grade for this course and must include sensing, planning, and actuation components on real hardware. Whereas the 106A project was an implementation-based project, this project should be research-based. Project deliverables include a proposal, a live demo and poster session, an academic-style paper, a small website, and several intermediate check-ins. Further information will be forthcoming.
Due to the types of deliverables involved (e.g., live demonstrations), extension days may not be used on project deliverables, and late work will not be accepted.
As in EECS C106A, all students must complete a final project. Failure to complete a final project will result in a failing grade.
Office Hours
The instructors will hold weekly office hours to discuss lecture content, homework assignments, projects, and other course material. We will try our best to schedule them so that each student has the opportunity to attend at least one office hour each week. When discussing a current homework assignment, instructors will not provide solutions. Rather, instructors will be happy to help clarify fundamentals and to guide students’ reasoning in related problems.
Content questions can go to any TA or the professor. Questions regarding homeworks should be directed to Max and Tarun. Questions regarding projects can be directed to any TA. Questions regarding course logistics should be directed to Tarun. All questions can be directed to Ed for the fastest response. When emailing staff, please prefix the subject line with [EECS 106B].
Grading
Grade Breakdown
| Homeworks | 20% |
| Midterm | 15% |
| Paper Presentations | 5% |
| Projects 1-5 | 30% |
| Final Project | 30% |
One feedback survey will be posted after the midterm, worth an extra 0.5% of your grade. An additional 0.5% will be granted for completing the end-of-semester university feedback.
Effort, Participation, and Altruism (EPA) Points
We want to reward you for engaging respectfully with the course! You are eligible to earn up to 2% extra credit via Effort, Participation, Altruism (EPA) points. These points can be earned in a variety of ways:
- Attending lecture and discussion
- Asking questions in class
- Helping others in lab section
- Answering questions on Ed
- Coming to Office Hours and Homework Party
- Actively engaging in journal club
Please remember to treat your peers (and hopefully your instructors!) with kindness and respect.
A Note on Late Work
While we will abide by the policies listed above regarding specific assignment types, we understand that unforeseen circumstances do happen. If you feel that you will not be able to complete an assignment on time under the policies listed above due to truly extenuating circumstances, please inform a course instructor as soon as possible and before the associated deadline to discuss your situation. Once the deadline has passed, accommodations are unlikely.
Miscellaneous Information
Disability Accommodations & Emergencies
If you need disability-related accommodations in this class, please inform us immediately. Please see the professor or Tarun privately after class, or send us an email.
Collaboration Policy
Students are allowed—and in fact, encouraged—to collaborate on how to approach problems. This can include talking through approaches and whiteboarding together. However, each student is responsible for writing their own responses, both for typical written questions and coding assignments. Students should never be in possession of another student’s code.
Online material is also open to use. However, it must not be copied directly, and any references should be credited in your work. Using previous years’ solutions from 106B/206B or any other class constitutes plagiarism and will be punished accordingly.
When debugging, students are encouraged to come to office hours for assistance. If debugging with peers, we encourage you to do this in person with others in small groups. However, we understand that this is not always possible, so screen sharing code for debugging assistance is permissible. When debugging, please do so in pairs or very small groups, and always do so in controlled settings to minimize sharing answers.
Students should never screenshare their code or answers directly on public platforms like non-private posts on Ed, the class Discord, or Zoom rooms. Please note that screen sharing on Discord can be viewed even without directly joining the call, so there can be no record of who is viewing your stream at any time. ALWAYS list collaborators.
tl;dr: Work together on approach, but write your own answers. If you need direct help debugging, ask a TA for help, or do so in controlled environments where the only people who see your code are your approach collaborators. ALWAYS list collaborators and cite sources on your submissions.
Regrade Requests
If you feel that your work has been graded unfairly, you may request a regrade by submitting a request on Gradescope with a statement explaining the mistake. Be aware that points may be deducted as well as added if a regrade is requested.
Advice
The following tips are offered based on our experience.
Do the homeworks! The homeworks are explicitly designed to help you to learn the material as you go along. There is usually a strong correlation between homework scores and final grades in the class.
Keep up with lectures! Discussion sections, labs, and homeworks all touch on portions of what we discuss in lecture. Students do much better if they stay on track with the course. That will also help you keep the pace with your homework and study group.
Take part in discussion sections! Discussion sections are not auxiliary lectures. They are an opportunity for interactive learning. The success of a discussion section depends largely on the willingness of students to participate actively in it. As with office hours, the better prepared you are for the discussion, the more you are likely to benefit from it.
Come to office hours! We love to talk to you and do a deep dive to help you understand the material better.
Form study groups! You are encouraged to form small groups (two to four people) to work together on homeworks and on understanding the class material on a regular basis. In addition to being fun, this can save you a lot of time by generating ideas quickly and preventing you from getting hung up on some point or other. Of course, it is your responsibility to ensure that you contribute actively to the group; passive listening will likely not help you much. Also, recall the caveat above, that you must write up your solutions on your own. We strongly advise you to spend some time on your own thinking about each problem before you meet with your study partners; this way, you will be in a position to compare ideas with your partners, and it will get you in practice for the exams. Make sure you work through all problems yourself, and that your final write-up is your own. Some groups try to split up the problems (“you do Problem 1, I’ll do Problem 2, then we’ll swap notes”); not only is this a punishable violation of the university’s collaboration policies, it also ensures you will learn a lot less from this course.